I try to accelerate my two class SSD model through tensorRT3. But there is an odd error in the first few layers like Convolution ,Pooling and ReLU. I found the data(blob) are transposed in each channel.The data show as follows. By the way, the input data is zeros mat.
pool3 blob:
data in caffe (get by python and caffe, shape:63*63):
The red color is the first column of the blob in caffe, and the green color is the second column of the blob in caffe. And the index of the green is 63. So it looks like there is a transpose in the W and H. And I check some other blobs in the first few layers. That’s the same case.
So what may cause this problem? Whether there some errors in my weights model?
This problem is probably because the weight model has been processed, maybe the Low rank decomposition, not sure…
But I tried the source model brfore these processing. And it works.
Thanks for your sharing. We have a quick check on your code.
It looks complicated and not easy for us to debug where the issue comes from.
Could you help to simplify this source? Maybe one transpose layer should be enough?
Hi, I am also trying to accelerate SSD with TensorRT, do you have any guidelines on how I should so so? My platform is the Jetson TX2, should I then use TensorRT 3.0 or 2.1 on it?
Hi Aasta, I have installed TensorRT on my host PC(for testing) with a GTX 1070 by downloading the tar file and adding the path to the library environment variable(I did not install the python TensorRT package though) When I try to build your Face-recognition example I get the following error:
fatal error: NvCaffeParser.h: No such file or directory
#include "NvCaffeParser.h"
I am able to run for instance sampleFasterRCNN from within the TensorRT-3.0.1 folder though. What should I do to fix this error?
I installed TensorRT 3.0.1, could it be that Face-recognition only works with TensorRT 2.1?
Edit: I was able to find a temporary fix by manually setting ${GIE_PATH} manually in the CMakeLists.txt. Though it still crashes because it is unable to find -lncaffe_parser and -lnvinfer
Face recognition is a TensorRT 2.1 sample of Jetson.
If you want to use it on desktop GPU, there are some configuration should be updated to the x86 environment.